Hemlata Tak
Research Subjects
Research Interests
Hemlata Tak has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Hye-Jin Shim
University of Eastern Finland Finland
1 shared publication - Jee-Weon Jung
Carnegie Mellon University USA
1 shared publication Junichi Yamagishi
National Institute of Informatics Japan
1 shared publicationKong Aik Lee
Institute for Infocomm Research A
1 shared publicationMassimiliano Todisco
Eurecom France
1 shared publicationMin Hyun Han
Seoul National University South Korea
1 shared publication
Latest Publications
- Open Access
Towards single integrated spoofing-aware speaker verification embeddings
This study aims to develop a single integrated spoofing-aware speaker verification (SASV) embeddings that satisfy two aspects. First, rejecting non-target speakers' input as well as target speakers' spoofed inputs should be addressed. Second, competitive performance should be demonstrated compared to the fusion of automatic speaker verification (ASV) and countermeasure (CM) embeddings, which outperformed single embedding solutions by a large margin in the SASV2022 challenge. We analyze that the inferior performance of single SASV embeddings comes from insufficient amount of training data and distinct nature of ASV and CM tasks. To this end, we propose a novel framework that includes multi-stage training and a combination of loss functions. Copy synthesis, combined with several vocoders, is also exploited to address the lack of spoofed data. Experimental results show dramatic improvements, achieving a SASV-EER of 1.06% on the evaluation protocol of the SASV2022 challenge.
Open AccessTowards single integrated spoofing-aware speaker verification embeddings
This study aims to develop a single integrated spoofing-aware speaker verification (SASV) embeddings that satisfy two aspects. First, rejecting non-target speakers' input as well as target speakers' spoofed inputs should be addressed. Second, competitive performance should be demonstrated compared to the fusion of automatic speaker verification (ASV) and countermeasure (CM) embeddings, which outperformed single embedding solutions by a large margin in the SASV2022 challenge. We analyze that the inferior performance of single SASV embeddings comes from insufficient amount of training data and distinct nature of ASV and CM tasks. To this end, we propose a novel framework that includes multi-stage training and a combination of loss functions. Copy synthesis, combined with several vocoders, is also exploited to address the lack of spoofed data. Experimental results show dramatic improvements, achieving a SASV-EER of 1.06% on the evaluation protocol of the SASV2022 challenge.